Ali Batuhan Bayırlı

Dr. Ali Batuhan Bayırlı

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 October 2024 in Archives of Oral Biology
Verified
Journal Article
Closed access
Ali Batuhan BayırlıAli Batuhan Bayırlı
Ali Batuhan Bayırlı
CGCeyda Gürhan
Ceyda Gürhan
ESErcan Saruhan
Ercan Saruhan

2 June 2025 in Clinical Oral Investigations
Verified
Journal Article
Open access
PDF file
EYEbru Yurdakurban
Ebru Yurdakurban
Ali Batuhan BayırlıAli Batuhan Bayırlı
Ali Batuhan Bayırlı
MUMEHMETCAN UYTUN
MEHMETCAN UYTUN
ÖSÖznur Suçeken
Öznur Suçeken
OKOnur Karasoy
Onur Karasoy
KTKübra Gülnur TOPSAKAL
Kübra Gülnur TOPSAKAL
Objective: The aim of this study was to develop convolutional neural network (CNN)-based systems to diagnose calculus, plaque, gingival hyperplasia and gingival inflammation in intraoral images from orthodontic patients. Materials and methods: A dataset of 1,000 lateral and frontal intraoral images from orthodontic patients was used to develop CNN-based models. Periodontology specialists annotated areas of dental calculus, plaque, gingival inflammation, and gingival hyperplasia on the teeth and gingiva. The dataset was divided into training (80%), validation (10%), and test (10%) sets for model development. The YOLOv8 and hybrid U-Net + ResNet50 models were examined. Their performance was evaluated on the basis of accuracy, precision, recall, F 1 score, Tversky loss, intersection over union, mean average precision, Dice coefficient, and Cohen’s kappa. Results: The mean classification accuracy was 0.96 for the YOLOv8 model and 0.93 for the U-Net + ResNet50 model. On the basis of the Dice coefficient, the models performed best in detecting gingival hyperplasia (YOLOv8: 0.78, U-Net + ResNet50: 0.79) and worst in detecting dental calculus (YOLOv8:0.48, U-Net + ResNet50:0.53). Cohen’s kappa coefficient was highest for classifying gingival hyperplasia (YOLOv8: 0.785, U-Net + ResNet50: 0.790). The precision exceeded 0.72 across all the classifications, with the greatest precision in classifying gingival inflammation. Conclusion: Deep learning-based systems can serve as decision support tools by offering rapid and objective evaluations of dental calculus, plaque, gingival inflammation, and gingival hyperplasia. Nonetheless, the definitive diagnostic conclusion should be based on the clinician’s specialized expertise and professional judgment. Clinical relevance: The integration of CNN-based diagnostic models into clinical workflows has the potential to facilitate early periodontal diagnosis and improve accessibility to periodontal assessments in orthodontic patients.

19 January 2026 in Diagnostics
Verified
Journal Article
Open access
PDF file
Ali Batuhan BayırlıAli Batuhan Bayırlı
Ali Batuhan Bayırlı
BKBuse Kesgin
Buse Kesgin
MUMEHMETCAN UYTUN
MEHMETCAN UYTUN
AKAlican Kuran
Alican Kuran
MÇMesude Çitir
Mesude Çitir
KOKaan Orhan
Kaan Orhan
Background/Objective: Bitewing radiographs are widely used for evaluating dental caries, restorations, and periodontal status due to their low radiation dose and high image quality. While artificial intelligence–based studies are common for other dental imaging modalities, multi-class diagnostic charting on bitewing radiographs remains limited. This study aimed to simultaneously detect eight periodontal and restorative parameters using a YOLOv8x-seg–based deep learning model and to assess its diagnostic performance. Materials and Methods: A total of 1197 digital bitewing radiographs were retrospectively analyzed and annotated by experts, resulting in 7860 labels across eight conditions. Periodontal conditions included alveolar bone loss, dental calculus, and furcation defects, while restorative and dental conditions comprised caries, cervical marginal gaps, open contacts, overhanging fillings, and secondary caries. The dataset was divided on a patient basis into training (80%), validation (10%), and test (10%) sets. The YOLOv8x-seg model was trained for 800 epochs with extensive data augmentation, and performance was evaluated using precision, recall, and F1-score, along with confusion matrices. Results: The model showed the highest accuracy in the alveolar bone loss class (precision: 0.84, recall: 0.93, F1: 0.88). While moderate performance was achieved for dental calculus (F1: 0.58) and caries (F1: 0.57) detection, lower scores were recorded in low-frequency classes such as cervical marginal gap (F1: 0.23), secondary caries (F1: 0.29), overhanging filling (F1: 0.35), furcation defect (F1: 0.40), and open contact (F1: 0.41). The overall segmentation performance achieved an mAP@0.5 of 0.30 and an mAP@0.5:0.95 of 0.10, indicating an acceptable performance level for segmentation-based multi-class models. Conclusions: The obtained findings demonstrate that the YOLOv8x-seg architecture can detect and segment periodontal conditions with high success and restorative parameters with moderate success in automation processes in bitewing radiographs. Accordingly, the model presents a methodologically feasible framework for the multiple and simultaneous radiographic evaluation of periodontal and restorative findings on bitewing radiographs, with performance varying across classes and lower sensitivity observed in low-frequency conditions.

7 November 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
Ali Batuhan BayırlıAli Batuhan Bayırlı
Ali Batuhan Bayırlı
MUMEHMETCAN UYTUN
MEHMETCAN UYTUN
FTFULDEN CANTAS TURKIS
FULDEN CANTAS TURKIS
ESErcan Saruhan
Ercan Saruhan
HKHuseyin Gencay Keceli
Huseyin Gencay Keceli
Background/Objectives: This study aimed to evaluate salivary leptin, adiponectin, and calprotectin levels and to investigate the associations among these biomarkers in periodontally healthy individuals, as well as in patients with gingivitis and periodontitis. Methods: A total of 165 participants were included: 55 periodontally healthy individuals, 55 with gingivitis, and 55 with periodontitis. Unstimulated saliva was collected via passive drool, and salivary leptin, adiponectin, and calprotectin levels were biochemically quantified using enzyme-linked immunosorbent assay. Results: Salivary leptin levels were significantly lower in the periodontally healthy group than those in the gingivitis and periodontitis groups, whereas adiponectin levels were reduced in the periodontitis group than in the periodontally healthy and gingivitis groups (p < 0.05). Salivary calprotectin levels differed significantly among groups, highest in the periodontitis group, followed by the gingivitis and periodontally healthy groups (p < 0.05). Salivary leptin and calprotectin levels demonstrated significant positive correlations with all clinical periodontal parameters, while adiponectin levels were negatively correlated (p < 0.05). Receiver operating characteristic and logistic regression analyses identified salivary leptin, calprotectin, and adiponectin levels as significant biomarkers for distinguishing periodontal health, gingivitis, and periodontitis (p < 0.05). Conclusions: These findings suggest salivary leptin, calprotectin, and adiponectin may serve as biomarkers and potential risk predictors of periodontal disease.

26 September 2024 in Biomarkers in Medicine
Verified
Journal Article
Closed access
CGCeyda Gürhan
Ceyda Gürhan
ESErcan Saruhan
Ercan Saruhan
Ali Batuhan BayırlıAli Batuhan Bayırlı
Ali Batuhan Bayırlı
Aim: To examine whether there is any difference in the levels of salivary melatonin between bruxism and nonbruxism groups and to compare the stress and anxiety levels between the two groups. Materials & methods: Patients meeting the probable bruxism criteria according to the International Consensus on the Assessment of Bruxism Criteria were included in the bruxism group. The salivary melatonin concentrations of both groups were measured using an ELISA kit. To determine the relationship between stress and bruxism, the State-Trait Anxiety Inventory (STAI) test was used. Results: The bruxism group had a significantly lower night-time salivary melatonin level than the control group (p < 0.05). No significant difference was determined between the bruxism group and the control group in respect of the STAI-T scores (p > 0.05). Conclusion: The study findings revealed a strong relationship between a low melatonin level and bruxism.

3 November 2024 in International Journal of Secondary Metabolite
Verified
Journal Article
Open access
PDF file
Ali Batuhan BayırlıAli Batuhan Bayırlı
Ali Batuhan Bayırlı
IKİbRahim Kıvrak
İbRahim Kıvrak
ESErcan Saruhan
Ercan Saruhan
FTFULDEN CANTAS TURKIS
FULDEN CANTAS TURKIS
Natural antimicrobial products are attracting interest in the treatment of periodontal diseases due to their minimal or nonexistent side effects. Propolis, a complex resin content produced by bees, has drawn particular interest for its antibacterial effects, including inhibitory effects on periodontopathogenic bacterial species. This study compared the effects of propolis, a natural product, and chlorhexidine, the gold standard antimicrobial agent, on MMP-1 and MMP-9 levels in gingival crevicular fluid (GCF). Subgingival irrigations of chlorhexidine and propolis solutions were performed in selected deep periodontal pockets of periodontitis patients along with scaling and root planing. The treatment protocol was administered three times at one-month intervals starting from the initial day of the study. GCF MMP-1 and MMP-9 levels, along with clinical periodontal parameters, were evaluated before and after treatment. The study results showed that a statistically significant decrease in clinical periodontal parameters in both groups (p<0.001). Biochemical analysis revealed a statistically significant decrease in levels of GCF MMP-1 and MMP-9 in both groups (p<0.005). Additionally, the decrease in GCF MMP-1 levels was found to be significantly greater in the propolis group compared to the chlorhexidine group (p<0.001).